Raw scan report

Browse — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.8.0",
    "methodologyVersion": "mcptrustchecker-1.8"
  },
  "target": {
    "id": "@saiden/browse",
    "source": {
      "kind": "package",
      "origin": "@saiden/browse"
    },
    "server": {
      "name": "@saiden/browse"
    }
  },
  "grade": "D",
  "score": {
    "score": 62,
    "threatScore": 73,
    "grade": "D",
    "band": "D",
    "categorySubtotals": {
      "injection": 26.95,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-010",
        "category": "injection",
        "severity": "high",
        "confidence": "strong",
        "rawWeight": 22,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 15.4
      },
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-010",
        "category": "injection",
        "severity": "high",
        "confidence": "strong",
        "rawWeight": 22,
        "confidenceMult": 0.7,
        "diminishingFactor": 0.5,
        "appliedPenalty": 7.7
      },
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-010",
        "category": "injection",
        "severity": "high",
        "confidence": "strong",
        "rawWeight": 22,
        "confidenceMult": 0.7,
        "diminishingFactor": 0.25,
        "appliedPenalty": 3.85
      },
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "critical",
        "label": "capability blast radius (critical) — client exposure if the model is manipulated",
        "appliedPenalty": 10
      },
      {
        "kind": "client",
        "term": "verification-discount",
        "level": "repo",
        "label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
        "appliedPenalty": 1
      },
      {
        "kind": "client",
        "term": "coverage-honesty",
        "level": "source",
        "label": "inspection depth (source) — how much of the target the scan could see",
        "appliedPenalty": 0
      }
    ],
    "gatesFired": [],
    "methodologyVersion": "mcptrustchecker-1.8"
  },
  "capability": {
    "level": "critical",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "can send data / act on an external service",
      "can execute shell commands or code",
      "untrusted input can reach code execution"
    ],
    "tags": [
      "untrusted-input",
      "code-exec",
      "external-sink"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (40 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
    ]
  },
  "findings": [
    {
      "ruleId": "MTC-SRC-010",
      "title": "Dynamic evaluation of a non-literal value (dist/browser.d.ts)",
      "category": "injection",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/browser.d.ts:64`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/browser.d.ts"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-010",
        "file": "dist/browser.d.ts",
        "line": 64
      }
    },
    {
      "ruleId": "MTC-SRC-010",
      "title": "Dynamic evaluation of a non-literal value (dist/browser.js)",
      "category": "injection",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/browser.js:361`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/browser.js"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-010",
        "file": "dist/browser.js",
        "line": 361
      }
    },
    {
      "ruleId": "MTC-SRC-010",
      "title": "Dynamic evaluation of a non-literal value (dist/mcp.js)",
      "category": "injection",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/mcp.js:251`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/mcp.js"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-010",
        "file": "dist/mcp.js",
        "line": 251
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"eval\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"eval\" appears to run shell commands or evaluate code (keyword \"eval\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
      "remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
      "location": {
        "kind": "tool",
        "name": "eval"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (dist/browser.d.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/browser.d.ts:64`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/browser.d.ts"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "dist/browser.d.ts",
        "line": 64
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (dist/browser.integration.test.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/browser.integration.test.js:79`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/browser.integration.test.js"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "dist/browser.integration.test.js",
        "line": 79
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (dist/browser.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/browser.js:361`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/browser.js"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "dist/browser.js",
        "line": 361
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (dist/mcp.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/mcp.js:251`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/mcp.js"
      },
      "evidence": "eval(",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "dist/mcp.js",
        "line": 251
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/browser.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/browser.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/browser.js"
      },
      "evidence": "child_process",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/browser.js",
        "line": 1
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/chrome.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/chrome.js:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "dist/chrome.js"
      },
      "evidence": "child_process",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/chrome.js",
        "line": 15
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([html, metrics]) co-exist with external-action tools ([eval, upload]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
      "remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
      "location": {
        "kind": "flow",
        "name": "html → eval"
      },
      "evidence": "untrusted [html, metrics] → sinks [eval, upload]",
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "html",
          "metrics"
        ],
        "sinks": [
          "eval",
          "upload"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"eval\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"eval\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
      "remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
      "location": {
        "kind": "tool",
        "name": "eval"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "html",
        "metrics"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "eval",
        "upload"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "launch",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "goto",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "back",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "forward",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "reload",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "click",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "type",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "query",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "url",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "html",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"get_page\""
        ]
      }
    },
    {
      "tool": "screenshot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "preview",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "eval",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"eval\""
        ]
      }
    },
    {
      "tool": "console",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "network",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "intercept",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "errors",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "metrics",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"get_page\""
        ]
      }
    },
    {
      "tool": "a11y",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "dialog",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "cookies",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "storage",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "hover",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "select",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "keys",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "upload",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"upload_file\""
        ]
      }
    },
    {
      "tool": "scroll",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "viewport",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "emulate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "wait",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "close",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "session_save",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "session_restore",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "import",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "favicon",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "convert",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "resize",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "crop",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "compress",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "thumbnail",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "f71c0a79a818de4a7ebd77dfafffb421a63f8b8ea511bde4a0fbedfc4bc1e02e",
  "stats": {
    "tools": 40,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 10,
      "medium": 1,
      "low": 1,
      "info": 0
    }
  }
}